R @ MMC
Costas T Lambrew Research Retreat
May 1, 2019
Visualize your data
Create maps!
Statistics and machine learning
Programmatically generate tables
tbl_summary(trial[c("trt", "age", "grade", "response")],
by = "trt") %>%
add_comparison() | Characteristic1 | Drug, N = 107 | Placebo, N = 93 | p-value2 |
|---|---|---|---|
| Age, yrs | 47 (39, 58) | 45 (36, 54) | 0.3 |
| Unknown | 6 | 3 | |
| Grade | 0.3 | ||
| I | 38 (36%) | 29 (31%) | |
| II | 34 (32%) | 24 (26%) | |
| III | 35 (33%) | 40 (43%) | |
| Tumor Response | 53 (51%) | 30 (34%) | 0.023 |
| Unknown | 4 | 5 | |
| 1 Statistics presented: median (IQR); n (%) 2 Statistical tests performed: Wilcoxon rank-sum test; chi-square test of independence |
|||
MMC R server
Access your work from any MaineHealth computer with a web browser
MMC R server
Install packages with ease
install.packages("tidyverse")MMC R server
Use Python
import pandas as pd
my_series = pd.Series([2, 4, 6, 8, 10])
print(my_series.describe())## count 5.000000
## mean 6.000000
## std 3.162278
## min 2.000000
## 25% 4.000000
## 50% 6.000000
## 75% 8.000000
## max 10.000000
## dtype: float64MMC R server
Connect to databases
con <- dbConnect(odbc(), Driver = "{ODBC Driver 17 for SQL Server}",
Server = "localhost",
Database = "testdb",
UID = "SA",
PWD = rstudioapi::askForPassword("Database password"),
Port = 1433)MMC R user group
- Get help from peers
- Meets first Tuesday of every month at CORE
- Upcoming topics
- Programmatic tables (Next Tuesday)
- Baysian multilevel modeling
- Causal inference and Structural Equation Modeling
- Big data